Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and functions related to programming and CUDA errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    checking technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.67
    windowFixed
    -0.65
    :✨
    -0.61
    EndGlobalSection
    -0.60
     CreateTagHelper
    -0.57
    twimg
    -0.56
    demies
    -0.56
     AssemblyVersion
    -0.53
    دانشنامهٔ
    -0.53
    AddTagHelper
    -0.52
    POSITIVE LOGITS
     cur
    0.39
     check
    0.38
     checked
    0.36
    ElementException
    0.35
     checking
    0.34
     boy
    0.34
    ぐ
    0.33
     temper
    0.33
     ang
    0.33
     imp
    0.32
    Act Density 0.087%

    No Known Activations